Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines

In this paper, the time variation of signals from several SCADA systems of geographically closed turbines are analysed and compared. When operating correctly, they show a clear pattern of joint variation. However, the presence of a failure in one of the turbines causes the signals from the faulty tu...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Marti Puig, Pere, Cusidó, Jordi, Lozano, Francisco J., Serra Serra, Moises, Caiafa, Cesar Federico, Solé Casals, Jordi
Formato: Articulo
Lenguaje:Inglés
Publicado: 2022
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/155781
Aporte de:
id I19-R120-10915-155781
record_format dspace
spelling I19-R120-10915-1557812023-08-02T20:04:08Z http://sedici.unlp.edu.ar/handle/10915/155781 Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines Marti Puig, Pere Cusidó, Jordi Lozano, Francisco J. Serra Serra, Moises Caiafa, Cesar Federico Solé Casals, Jordi 2022-10 2023-08-02T18:32:40Z en Ingeniería Astronomía wind turbine fault diagnosis renewable energy feature engineering normal behaviour models In this paper, the time variation of signals from several SCADA systems of geographically closed turbines are analysed and compared. When operating correctly, they show a clear pattern of joint variation. However, the presence of a failure in one of the turbines causes the signals from the faulty turbine to decouple from the pattern. From this information, SCADA data is used to determine, firstly, how to derive reference signals describing this pattern and, secondly, to compare the evolution of different turbines with respect to this joint variation. This makes it possible to determine whether the behaviour of the assembly is correct, because they maintain the well-functioning patterns, or whether they are decoupled. The presented strategy is very effective and can provide important support for decision making in turbine maintenance and, in the near future, to improve the classification of signals for training supervised normality models. In addition to being a very effective system, it is a low computational cost strategy, which can add great value to the SCADA data systems present in wind farms. Instituto Argentino de Radioastronomía Articulo Articulo http://creativecommons.org/licenses/by/4.0/ Creative Commons Attribution 4.0 International (CC BY 4.0) application/pdf
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ingeniería
Astronomía
wind turbine
fault diagnosis
renewable energy
feature engineering
normal behaviour models
spellingShingle Ingeniería
Astronomía
wind turbine
fault diagnosis
renewable energy
feature engineering
normal behaviour models
Marti Puig, Pere
Cusidó, Jordi
Lozano, Francisco J.
Serra Serra, Moises
Caiafa, Cesar Federico
Solé Casals, Jordi
Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines
topic_facet Ingeniería
Astronomía
wind turbine
fault diagnosis
renewable energy
feature engineering
normal behaviour models
description In this paper, the time variation of signals from several SCADA systems of geographically closed turbines are analysed and compared. When operating correctly, they show a clear pattern of joint variation. However, the presence of a failure in one of the turbines causes the signals from the faulty turbine to decouple from the pattern. From this information, SCADA data is used to determine, firstly, how to derive reference signals describing this pattern and, secondly, to compare the evolution of different turbines with respect to this joint variation. This makes it possible to determine whether the behaviour of the assembly is correct, because they maintain the well-functioning patterns, or whether they are decoupled. The presented strategy is very effective and can provide important support for decision making in turbine maintenance and, in the near future, to improve the classification of signals for training supervised normality models. In addition to being a very effective system, it is a low computational cost strategy, which can add great value to the SCADA data systems present in wind farms.
format Articulo
Articulo
author Marti Puig, Pere
Cusidó, Jordi
Lozano, Francisco J.
Serra Serra, Moises
Caiafa, Cesar Federico
Solé Casals, Jordi
author_facet Marti Puig, Pere
Cusidó, Jordi
Lozano, Francisco J.
Serra Serra, Moises
Caiafa, Cesar Federico
Solé Casals, Jordi
author_sort Marti Puig, Pere
title Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines
title_short Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines
title_full Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines
title_fullStr Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines
title_full_unstemmed Detection of Wind Turbine Failures through Cross-Information between Neighbouring Turbines
title_sort detection of wind turbine failures through cross-information between neighbouring turbines
publishDate 2022
url http://sedici.unlp.edu.ar/handle/10915/155781
work_keys_str_mv AT martipuigpere detectionofwindturbinefailuresthroughcrossinformationbetweenneighbouringturbines
AT cusidojordi detectionofwindturbinefailuresthroughcrossinformationbetweenneighbouringturbines
AT lozanofranciscoj detectionofwindturbinefailuresthroughcrossinformationbetweenneighbouringturbines
AT serraserramoises detectionofwindturbinefailuresthroughcrossinformationbetweenneighbouringturbines
AT caiafacesarfederico detectionofwindturbinefailuresthroughcrossinformationbetweenneighbouringturbines
AT solecasalsjordi detectionofwindturbinefailuresthroughcrossinformationbetweenneighbouringturbines
_version_ 1807220850143789056